Automatic Airway Segmentation in chest CT using Convolutional Neural Networks

TL;DR

This paper introduces a robust 3D Unet-based method for automatic airway segmentation in chest CT scans, achieving high accuracy despite the complexity of airway structures.

Contribution

It applies a 3D Unet architecture with optimized loss functions and data augmentation for airway segmentation, demonstrating improved performance over previous methods.

Findings

Achieved an average dice coefficient of 0.8.

Evaluated the impact of loss functions and data augmentation.

Validated on a dataset of 18 CT scans.

Abstract

Segmentation of the airway tree from chest computed tomography (CT) images is critical for quantitative assessment of airway diseases including bronchiectasis and chronic obstructive pulmonary disease (COPD). However, obtaining an accurate segmentation of airways from CT scans is difficult due to the high complexity of airway structures. Recently, deep convolutional neural networks (CNNs) have become the state-of-the-art for many segmentation tasks, and in particular the so-called Unet architecture for biomedical images. However, its application to the segmentation of airways still remains a challenging task. This work presents a simple but robust approach based on a 3D Unet to perform segmentation of airways from chest CTs. The method is trained on a dataset composed of 12 CTs, and tested on another 6 CTs. We evaluate the influence of different loss functions and data augmentation techniques, and reach an average dice coefficient of 0.8 between the ground-truth and our automated segmentations.